Using Artificial Neural Networks (ANN) for Modeling Predicting Hardness Change of Wood during Heat Treatment

In this study, an artificial neural network (ANN) model was built to study the relationship between the process parameters of heat treatment and the hardness of wood. Three important parameters: temperature (170, 180, 190, 200 and 210°C), treatment time (2, 4, 6 and 8h), and wood species (Larch and Poplar) were considered as the inputs to the neural network. There were four neurons in the hidden layer that were used, and an output layer as wood hardness. According to the results, the mean absolute percentage errors (MAPE) were determined as 0.1167%, 0.355% and 1.34% in the prediction of wood hardness values for training, validation, and testing data sets. Determination coefficients (R2) greater than 0.99 were obtained for all data sets with the proposed ANN models. These results show that ANN models can be used successfully for predicting hardness changes hardness of wood during heat treatment. (paper)